tinker495 / JAxtar
JAxtar is a project with a JAX-native implementation of parallelizeable A* & Q* solver for neural heuristic search research.
☆17Updated this week
Alternatives and similar repositories for JAxtar:
Users that are interested in JAxtar are comparing it to the libraries listed below
- Jax-Baseline is a Reinforcement Learning implementation using JAX and Flax/Haiku libraries, mirroring the functionality of Stable-Baselin…☆50Updated this week
- Deep Multi-Agent Reinforcement Learning with StarCraft 2☆10Updated 4 years ago
- Scalable distributed reinforcement learning agents on kubernetes☆57Updated last year
- Yet Another Reinforcement Learning Tutorial☆73Updated 2 years ago
- Distributed Priortized Experience Replay☆10Updated 6 years ago
- Brain Agent for Large-Scale and Multi-Task Agent Learning☆93Updated last year
- Various reinforcement learning algorithms written in Jax + Flax☆24Updated last year
- JAX-based Spiking Neural Network framework☆60Updated 3 years ago
- ☆61Updated last year
- Simple implementations of multi-agent evolutionary strategies using pytorch.☆16Updated 3 years ago
- An implementation of DreamerV2 written in JAX, with support for running multiple random seeds of an experiment on a single GPU.☆15Updated 2 years ago
- Deep Reinforcement Learning Algorithms Implementation in PyTorch☆27Updated 2 months ago
- ☆21Updated 3 years ago
- An implementation of MuZero in JAX.☆56Updated 2 years ago
- ML2-Multi Agent Environments☆34Updated last year
- Accelerated replay buffers in JAX☆41Updated 2 years ago
- ☆10Updated 6 years ago
- Unity로 멀티 에이전트 강화학습(MARL) 수행하기 위한 프레임 워크 제공☆23Updated 3 years ago
- Standardized Minecraft Diamond Environment for Reinforcement Learning☆26Updated last year
- A number of agents (PPO, MuZero) with a Perceiver-based NN architecture that can be trained to achieve goals in nethack/minihack environm…☆41Updated 2 years ago
- Experiment. Plot. Tabulate.☆69Updated 8 months ago
- A C++ pytorch implementation of MuZero☆38Updated last year
- Code for "SimbaV2: Hyperspherical Normalization for Scalable Deep Reinforcement Learning"☆44Updated last week
- ☆18Updated last year
- Reinforcement learning in pure JAX.☆12Updated 2 months ago
- flexible meta-learning in jax☆13Updated last year
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weights…☆54Updated 2 years ago
- General Modules for JAX☆64Updated last month
- ☆51Updated 2 years ago
- Flax Implementation of DreamerV3 on Crafter☆14Updated 2 months ago